检索结果-内蒙古大学图书馆

16th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2023

作者： Ma, Lerong Li, Shanshan Tang, Xiaomin Tianjin University of Technology and Education Tianjin Key Laboratory of Information Sensing & Intelligent Control School of Automation and Electrical Engineering Tianjin China

ISBN: (纸本)9798350330755

An adaptive fuzzy closed-loop control method using linear feedback technology was proposed to inhibit epileptiform activity simulated by a neural mass model. In this study, the problem of epileptic suppression was considered as a typical control problem. First, the neural mass model was introduced to simulate neural firings at all stages of epileptic seizure;secondly, an adaptive fuzzy closed-loop control strategy was designed to suppress epileptiform firings of neural mass model;finally, the control effect of this adaptive fuzzy closed-loop control was compared with incremental PI closed-loop control. The results showed that the adaptive fuzzy closed-loop control consumes less control energy and achieves better control effect comparing with the incremental PI control algorithm. In addition, the adaptive closed-loop control can adjust the parameters in real time according to the epilepsy state and does not depend on the change of model parameters, which providing a theoretical basis for individualized medical treatment. © 2023 IEEE.

关键词： Closed loop control systems

来源：评论

学校读者我要写书评

暂无评论

Emotion recognition based on CNN-SVM from EEG signals 5

Emotion recognition based on CNN-SVM from EEG signals

引用

5th Asia Symposium on Image Processing, ASIP 2023

作者： Jia, Yuyu Han, Chunxiao Tong, Wenhui Pei, Yue Tianjin University of Technology and Education School of Automation and Electrical Engineering Tianjin Key Laboratory of Information Sensing & Intelligent Control Tianjin China

ISBN: (纸本)9798350323429

Emotion recognition is an important research directions in the field of artificial intelligence. In this paper, we adopted deep learning methods to try to improve the performance of emotion recognition. First, we designed an experiment to induce three different emotions by video footage and collected corresponding EEG signals. Then, CNN-SVM algorithms were adopted to classify positive, neutral and negative emotions. Finally, the recognition performance of CNN-SVM for three-class emotion recognition was verified. It is found that CNN-SVM achieves a highest recognition accuracy of 99.98% and an average recognition accuracy of 98.53%, which is better than CNN alone. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Alertness Analysis from EEG Signals based on Temporal Complex Network Features 16

Alertness Analysis from EEG Signals based on Temporal Comple...

引用

16th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2023

作者： Wei, Beibei Han, Chunxiao Chen, Yi Che, Yanqiu Qin, Yingmei Li, Shanshan Tianjin University of Technology and Education Tianjin Key Laboratory of Information Sensing & Intelligent Control School of Automation and Electrical Engineering Tianjin China

ISBN: (纸本)9798350330755

Fatigue driving is a major contributor to traffic accidents, as it reduces alertness and can even be fatal. To investigate alertness changes during prolonged driving, we first built a simulated driving experiment platform and designed an alertness detection experiment. Electroencephalogram (EEG) signals were collected during prolonged fatigue driving from 16 subjects. For each subject, the driving process was divided into eight stages from T0-T7. Then, the alertness level was analyzed by temporal complex network method based on multiplex limited penetrable visibility graphs from the collected EEG signals. The clustering coefficient, path length and global efficiency of the constructed complex network were extracted for each driving stage under five typical brain rhythms including delta, theta, alpha, beta, and gamma. The results indicate that after a long stage of driving, the clustering coefficient and path length show an overall increasing trend, while the global efficiency reveals an overall decreasing trend. Our findings may provide indicators for monitoring alertness level. © 2023 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Ensemble-based Offline Data-driven Evolutionary Optimization for Operation Parameter of Blast Furnace 20

Ensemble-based Offline Data-driven Evolutionary Optimization...

引用

20th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2024

作者： Ye, Qiucheng Cai, Hongxia Bian, Yunqi School of Mechatronic Engineering and Automation Shanghai University Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai China

ISBN: (纸本)9798350356328

Stable control of the iron-making process through the adjustment of operating parameters is essential to improve blast furnace productivity. However, due to the complex and dynamic nature of the reaction process, it is difficult to perform accurate modeling and simulation experiments for a blast furnace. This poses great difficulties in performing the evaluation of control strategies in real-time. Offline evolutionary optimization, as an optimization technique that relies only on historical data, enables the search for optimal operation parameters through the introduction of surrogates. Based on the characteristics of historical time-series data of the iron-making process, this study proposes an offline evolutionary optimization method based on advanced time-series surrogates. Ensemble strategy combining surrogates with different prediction time windows contributes robustness during the optimization process. Additionally, multiple sub-regions are maintained to enable extensive searching of the decision space with a multi-objective nature. The efficiency of the proposed pooling method is demonstrated through verification in actual production cases. © 2024 IEEE.

关键词： Blast furnaces

来源：评论

学校读者我要写书评

暂无评论

An Improved YOLOv5 Algorithm for Elderly Fall Detection 12

An Improved YOLOv5 Algorithm for Elderly Fall Detection

引用

12th International Conference on Innovation, Knowledge, and Management, ICIKM 2023

作者： Wu, Han Zhao, Xueling Qiao, Jianghe Che, Yanqiu School of Automation and Electrical Engineering Tianjin University of Technology and Education Tianjin Key Laboratory of Information Sensing & Intelligent Control Tianjin China

ISBN: (纸本)9798350303315

Accidental falls are one of the major threats to the elderly population. Older adults who are not caught in time after a fall may miss the best time to be rescued. We propose an improved YOLOv5 fall detection algorithm in this paper. Firstly, we use SIoU Loss instead of CIoU Loss to improve the speed of training and the accuracy of inference. Secondly, the SimAM attention mechanism is introduced into the YOLOv5 model to further improve the model's performance. Experiments show that the mAP@0.5 of the improved YOLOv5 fall detection model reaches 96.7%, which is 2.4% higher than the original YOLOv5. The overall detection effect is better than the original YOLOv5 model and other network algorithms. The algorithm used in this paper can detect fall behavior promptly, which largely alleviates the risk of death or long-term treatment. © 2023 IEEE.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Features Extraction of Different Emotional based on Brain Rhythm 5

Features Extraction of Different Emotional based on Brain Rh...

引用

5th Asia Symposium on Image Processing, ASIP 2023

作者： Liu, Yanli Han, Chunxiao Tong, Wenhui Liu, Junxiu Qin, Yingmei Che, Yanqiu Tianjin University of Technology and Education School of Automation and Electrical Engineering Tianjin Key Laboratory of Information Sensing & Intelligent Control Tianjin China

ISBN: (纸本)9798350323429

Emotions are an essential part of human physiological performance. Therefore, the study of emotion recognition is extremely relevant in both practical applications and theoretical research. Based on the electroencephalogram (EEG) data we collected, this paper explored the differences from five different characteristics among the coefficient of variation (CV) , power spectral density (PSD) , differential entropy (DE) , approximate entropy (AE) , and permutation entropy (PE) of three emotions at different rhythms, analyzed the activity of each brain region under different emotions. Finally, this paper also compares the classification accuracy of single features and combined features. The experimental results reveal that emotions are more strongly correlated with Beta and Gamma bands;temporal lobe regions are most active in emotion-related brain activity;and the accuracy of combined features is higher than the accuracy of single feature classification. The experiment conclusively demonstrates that effective feature extraction and selection have far-reaching implications for emotion recognition. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning for optimal tracking of large-scale systems with multitime scales

引用

Science China(Information Sciences) 2023年第7期66卷 5-29页

作者： Jinna LI Hao NIE Tianyou CHAI Frank L.LEWIS School of Information and Control Engineering Liaoning Petrochemical University State Key Laboratory of Synthetical Automation for Process Industries Northeastern University UTA Research Institute University of Texas at Arlington

This paper aims to solve an optimal tracking control(OTC) problem of large-scale systems with multitime scales and coupled subsystems using singular perturbation(SP) theory and reinforcement learning(RL) techniques. A considerable contribution of this paper is the development of a data-driven SP-based RL method for the OTC of unknown large-scale systems with multitime scales. To achieve this, a multitime scale tracking problem was decomposed into a linear quadratic tracker problem for slow subsystems and a dynamical game problem for fast subsystems using the SP theory. Then, the distributed composite feedback controllers were found using a distributed off-policy integral RL algorithm that uses only measured data from the system in real time. Thus, the operational index can follow its prescribed target value via an approximately optimal approach. Theoretical analysis and proof are presented to demonstrate that the sum of the performances of reduced-order subsystems is approximately equal to the performance of the original large-scale system. Finally, numerical and practical examples are provided to validate the effectiveness of the proposed method.

关键词： reinforcement learning singular perturbation multitime scales data-driven control

来源：评论

学校读者我要写书评

暂无评论

Improved YOLOv3 and U-Net Based Pipetting Abnormal Condition Identification and Pipetting Region Segmentation

Improved YOLOv3 and U-Net Based Pipetting Abnormal Condition...

引用

2023 European Conference on Communication Systems, ECCS 2023

作者： Zhang, Zhiyu Li, Huiyan Liu, Yeming Tianjin University of Technology and Education Tianjin Key Laboratory of Information Sensing & Intelligent Control School of Automation and Electrical Engineering Tianjin China

ISBN: (纸本)9798350323344

To improve the reliability of micro pipetting in automatic pipetting workstations, this paper analyzes and investigates the problems related to abnormal condition recognition and pipetting volume detection during pipetting using deep learning models. Firstly, the YOLOv3 network model is designed to be lightweight, and the DarkNet-53 network, which is the backbone of the network structure for image feature information extraction, is replaced by the MobileNetv3 network to realize the recognition of abnormal conditions such as empty aspiration, air bubbles and blockage during pipetting;then the U-Net network model is built to integrate the CBAM attention mechanism module and the residual module to realize the segmentation of pipetting areas. Then, we construct a U-Net network model incorporating the CBAM attention mechanism module and residual module to segment the pipetting area. The results showed that the model size of the improved YOLOv3 network was reduced by 139.1 MB and the frame rate per second (FPS) was increased by 15.7 frames/s. The improved U-Net network improved the IOU and F1 values for pipetting area segmentation by 8% and 13% respectively. © 2023 IEEE.

关键词： Process monitoring

来源：评论

学校读者我要写书评

暂无评论

Automatic Schizophrenia Detection from Scalp EEG Using CNN with Wide Convolutional Kernel and ELM 5

Automatic Schizophrenia Detection from Scalp EEG Using CNN w...

引用

5th Asia Symposium on Image Processing, ASIP 2023

作者： Wei, Chun Qin, Yingmei Liu, Jing Jiang, Lijie Che, Yanqiu Tianjin University of Technology and Education School of Automation and Electrical Engineering Tianjin Key Laboratory of Information Sensing & Intelligent Control Tianjin China

ISBN: (纸本)9798350323429

Detection of schizophrenia is of great significance in clinical practice. In conventional machine learning methods, manual feature extraction is required, which is a hard and time-consuming task. This paper proposes a hybrid model consisting of a convolutional neural network (CNN) with a wide convolution kernel and an extreme learning machine (ELM). By changing the size of the convolution kernel to form a suitable wide convolution kernel, and automatically extracting and optimizing the features of the scalp electroencephalogram (EEG), the performance of the model is effectively improved and accurate detection of schizophrenia is achieved. The input of this model is the original multi-channel EEG picture after short-time Fourier transform, and the output are two types of classification labels for schizophrenia and healthy people. In the end, the detection accuracy of schizophrenia reached 95.59%. This model has a powerful advantage in detecting schizophrenia. © 2023 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Image Sample Generation of Stator Surface Defects Based on Layer Mask Blending Generative Adversarial Network 23

Image Sample Generation of Stator Surface Defects Based on L...

引用

9th International Conference on Computing and Artificial Intelligence, ICCAI 2023

作者： Li, Wenzheng Tian, Lihua Sun, Zhigang Xiao, Li School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781450399029

In industrial production processes, defect inspection plays an important role in reducing the occurrence of failures and improving production efficiency. Data-driven algorithms represented by deep learning have made great progress in recent years, but need to face the problems of small quantity and poor quality of datasets when applied to industrial defect inspection. This paper proposes a layer mask blending-based generative adversarial network (LMBGAN) and optimizes the training process to generate high-quality surface defect samples. LMBGAN generates defect images and layer masks using the defect image decoder and layer mask decoder with the Pixel Shuffle operation. Inspired by the layer mask in computer painting, LMBGAN adopts the input image as the base layer and blends the defect foreground through the layer mask, giving it the ability to focus more on generating upper-layer defect images and reducing unnecessary background changes. LMBGAN additionally introduces adaptive discriminator augmentation and non-saturating logistic loss to promote model convergence under small datasets, effectively alleviating the problem of GAN training difficulties with limited data. The experiment results show that the proposed method can generate high-quality and diverse defect image samples through easily accessible normal samples, thus reducing the difficulty of obtaining rare defect image samples. © 2023 Copyright held by the owner/author(s).

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：